Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations, events, and businesses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gradient
    -0.69
    acon
    -0.68
    Query
    -0.67
    uated
    -0.65
    isson
    -0.64
    BIL
    -0.64
    Tweet
    -0.62
    ère
    -0.62
     wondered
    -0.61
    _-
    -0.60
    POSITIVE LOGITS
     world
    1.25
     vicinity
    1.09
     shortest
    1.08
     country
    1.06
     entire
    1.06
     midst
    1.05
     nation
    1.04
     universe
    0.99
     hemisphere
    0.95
     history
    0.95
    Act Density 0.107%

    No Known Activations